dicksondickson/Qwen3.5-4B-oQ6e-mtp-bf16-MLX

[!NOTE] Updated Oct 24, 2026: Re-quantized with oMLX 0.7.3.dev2 with improved oQe Quantization and Better Low-Bit oQ. Please re-download if you have an earlier copy.

This model is a quantization of:
https://huggingface.co/Qwen/Qwen3.5-4B

This model was quantized using oQ (oMLX 0.7.3.dev2) imatrix, mixed-precision quantization with Better Low-Bit oQ.

Important tensors are left at bf16 which is for Apple M3 chips and later.

Run the model using oMLX:
https://github.com/jundot/omlx